Compare AI models

Specifications
Parameters
7B—
Context window
32k1M
Benchmarks
MATH
56.6%81.1%
GSM8K
77.1%93.8%
Overview
CompanyMistralQwen
Release dateJul 16 2024Nov 15 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Qwen2.5-Turbo (1M) leads Mathstral 7B on 2 of the 2 benchmarks they both report (MATH, GSM8K). Mathstral 7B shipped 122 days before Qwen2.5-Turbo (1M), so benchmark comparisons should account for the intervening progress.

Context windows are 32k (Mathstral 7B) vs 1M (Qwen2.5-Turbo (1M)). Mathstral 7B is open weight, while Qwen2.5-Turbo (1M) is closed.

On MATH, Qwen2.5-Turbo (1M) leads at 81.1% vs Mathstral 7B at 56.6%. On GSM8K, Qwen2.5-Turbo (1M) leads at 93.8% vs Mathstral 7B at 77.1%.